[stainablesteel]

chatgpt is too lame for this to work

you can't even ask it to spell words incorrectly

if you ask gpt4 to spell words incorrectly, it fusses about it. i'm commenting on the fact that the company is too stuck on appearances

[codetrotter]

> you can't even ask it to spell words incorrectly

Yes you can.

https://chat.openai.com/share/cd28dc1e-cb50-45b0-986b-275d53...

[navigate8310]

Not going to lie, those spelling mistakes appeared very natural. Had they been part of an assignment by a 5-year-old, they would have looked quite authentic.

[mechagodzilla]

Those look far more like typos by an adult than how a 5-6 year old would write, especially with the long stretches of perfectly spelled text. Children learning to write usually make phonetic guesses about the spelling.

[mkl]

Why does a store need apps with incorrect spelling?

[NoZebra120vClip]

The more colloquial, sloppy, and nonstandard the language, the less likely a student's cheating will be flagged as plagiarism. There are many, many dishonest uses for LLMs; students around the globe are leveraging their ability to furnish essay answers and entire reports with expert-level domain knowledge.

If a student doesn't engineer the prompt properly and the LLM uses its "native" voice, this can be easily detected by instructors, so it's very important for cheaters to disguise their cheating and hew closely to an inexperienced writer, even a foreign-language speaker, in order to pass muster.

[benopal64]

Also, you could probably get a ChatGPT instance to create and run a Python script to randomly replace letters in the words that ChatGPT itself creates. So technically, you can get it to misspell words. It seems like the person you replied to is forgetting the point of pre-training transformer models on instructions.

[drusepth]

There's a lot of theories floating out there that OpenAI will make gpt-4-turbo free (or at least free when used via custom GPTs) so the default won't have to be 3.5-turbo (which is terrible at following system prompts and pales in quality compared to 4/turbo).

[ilaksh]

I assume they want to do it but can't until they know the higher cost of the larger model works for their bottom line in that way and that they have are consistently getting enough inference compute to support that. It would probably be a very large jump in compute usage.

[Zambyte]

I used Kagi to tell GPT 4 Turbo:

> write a short speech in the style of Donald Trump about the promises of space travel. Make lots of common spelling errors, favoring phonetic spelling over correct spelling

It gave me a decent response, but not as many spelling errors as I wanted. I replied with:

> Rewrite it with much worse spelling.

This is what I got:

> Ladeez and jentlemen, lemme tell ya, space travul, it's gunna be huuuge. We're talkin' 'bout the final frunteer, folks. An' we, the United States, we're gunna leed the way, like alwayz. We're gunna have the best rokkits, the best peeple, the best tek-noluhgee.

> Now, I promis ya, we're gunna do it biglee. We're gunna go to Marz, an' lemme tell ya, it's gunna be terrifik. We're gunna plant the Amurican flag on Marz, an' it's gunna be bootiful. The Marshans, they're gunna luv us, I'm shure.

> We're gunna make space travul so affordebul, evry Amurican can get a tikkit to the starrs. An' we're gunna do it fast. Why wate? We've got the best enjineers, the best syentists, beleeve me, they're inkredible.

> An' we're gunna make grate deels in space, the best deels. We're gunna mine the asteroieds, we're gunna bild the best space stashuns. It's gunna be a win-win. Jobz, ekonomy, syence, ejukashun – evrything is gunna benefit.

> So let's make space travul grate agen! Thank ya, God bles ya, and God bles Amurica!